Simon Willison’s Weblog

Mistral Small 3.1 on Ollama. Mistral Small 3.1 (previously) is now available through Ollama, providing an easy way to run this multi-modal (vision) model on a Mac (and other platforms, though I haven't tried those myself).

I had to upgrade Ollama to the most recent version to get it to work - prior to that I got a Error: unable to load model message. Upgrades can be accessed through the Ollama macOS system tray icon.

I fetched the 15GB model by running:

ollama pull mistral-small3.1

Then used llm-ollama to run prompts through it, including one to describe this image:

llm install llm-ollama
llm -m mistral-small3.1 'describe this image' -a https://static.simonwillison.net/static/2025/Mpaboundrycdfw-1.png

Here's the output. It's good, though not quite as impressive as the description I got from the slightly larger Qwen2.5-VL-32B.

I also tried it on a scanned (private) PDF of hand-written text with very good results, though it did misread one of the hand-written numbers.

# 8th April 2025, 10:07 pm / vision-llms, mistral, llm, ollama, generative-ai, ai, llms, local-llms

Function calling with Gemma (via) Google's Gemma 3 model (the 27B variant is particularly capable, I've been trying it out via Ollama) supports function calling exclusively through prompt engineering. The official documentation describes two recommended prompts - both of them suggest that the tool definitions are passed in as JSON schema, but the way the model should request tool executions differs.

The first prompt uses Python-style function calling syntax:

You have access to functions. If you decide to invoke any of the function(s), you MUST put it in the format of [func_name1(params_name1=params_value1, params_name2=params_value2...), func_name2(params)]

You SHOULD NOT include any other text in the response if you call a function

(Always love seeing CAPITALS for emphasis in prompts, makes me wonder if they proved to themselves that capitalization makes a difference in this case.)

The second variant uses JSON instead:

You have access to functions. If you decide to invoke any of the function(s), you MUST put it in the format of {"name": function name, "parameters": dictionary of argument name and its value}

You SHOULD NOT include any other text in the response if you call a function

This is a neat illustration of the fact that all of these fancy tool using LLMs are still using effectively the same pattern as was described in the ReAct paper back in November 2022. Here's my implementation of that pattern from March 2023.

# 26th March 2025, 8:23 pm / prompt-engineering, google, generative-ai, llm-tool-use, gemma, ai, llms, local-llms

Qwen2.5-VL-32B: Smarter and Lighter. The second big open weight LLM release from China today - the first being DeepSeek v3-0324.

Qwen's previous vision model was Qwen2.5 VL, released in January in 3B, 7B and 72B sizes.

Today's Apache 2.0 licensed release is a 32B model, which is quickly becoming my personal favourite model size - large enough to have GPT-4-class capabilities, but small enough that on my 64GB Mac there's still enough RAM for me to run other memory-hungry applications like Firefox and VS Code.

Qwen claim that the new model (when compared to their previous 2.5 VL family) can "align more closely with human preferences", is better at "mathematical reasoning" and provides "enhanced accuracy and detailed analysis in tasks such as image parsing, content recognition, and visual logic deduction".

They also offer some presumably carefully selected benchmark results showing it out-performing Gemma 3-27B, Mistral Small 3.1 24B and GPT-4o-0513 (there have been two more recent GPT-4o releases since that one, 2024-08-16 and 2024-11-20).

As usual, Prince Canuma had MLX versions of the models live within hours of the release, in 4 bit, 6 bit, 8 bit, and bf16 variants.

I ran the 4bit version (a 18GB model download) using uv and Prince's mlx-vlm like this:

uv run --with 'numpy<2' --with mlx-vlm \
  python -m mlx_vlm.generate \
    --model mlx-community/Qwen2.5-VL-32B-Instruct-4bit \
    --max-tokens 1000 \
    --temperature 0.0 \
    --prompt "Describe this image." \
    --image Mpaboundrycdfw-1.png

Here's the image:

And here's the resulting description, which I found to be very impressive:

This image appears to be a map highlighting specific areas along the coastline, likely in California, based on the geographical features and place names. Here is a detailed description of the image:

1. Geographic Features:

   • The map shows a section of the coastline, with land on the right and the sea on the left.
   • The land area includes parts of SanMateo County, as noted in the top-right corner.
   • The coastline features several named locations, including:
     • Point Montara
     • Pillar Point
     • Kings Rock
     • VicenteCreek
     • DennistonCreek
     • State Beach

2. Highlighted Areas:

   • The map contains two distinct areas marked with different colors:
     • Red Area (Top Section)
       • Labeled as "MONTARA" and "MONTARA M R" (possibly referring to a "Marine Reserves" or similar protected area).
       • This area is marked with a dark red color and extends from the coastline inland.
     • Blue Area (Bottom Section)
       • Labeled as "PILLAR" and "PILLAR P O I N T" along with "SMCA" (Special Management Area).
       • This area is marked with a blue color and is located closer to the coastline, including the area around "Pillar Point."

3. Depth Contours:

   • The map includes depth markings in the sea, indicating the bathymetrical features:
     • 20 fathom (fm) line is marked in the upper-left part of the sea.
     • 10 fathom (fm) line is marked closer to the coastline.
     • 30 fathom (fm) line is marked further out to sea.

4. Other Features:

   • State Beach: Marked near the top-right, indicating a protected recreational area.
   • Kings Rock: A prominent feature near the coastline, likely a rocky outcropping.
   • Creeks: The map shows several creeks, including VicenteCreek and DennistonCreek, which flow into the sea.

5. Protected Areas:

   • The map highlights specific protected areas:
     • Marine Reserves:
       • "MONTARA M R" (Marine Reserves) in red.
     • Special Management Area (SMCA)
       • "PILLAR P O I N T" in blue, indicating a Special Management Area.

6. Grid and Coordinates:

   • The map includes a grid with latitude and longitude markings:
     • Latitude ranges from approximately 37°25'N to 37°35'N.
     • Longitude ranges from approximately 122°22.5'W to 122°35.5'W.

7. Topography:

   • The land area shows topographic features, including elevations and vegetation, with green areas indicating higher elevations or vegetated land.

8. Other Labels:

   • "SMR": Likely stands for "State Managed Reserves."
   • "SMCA": Likely stands for "Special Management Control Area."

In summary, this map highlights specific protected areas along the coastline, including a red "Marine Reserves" area and a blue "Special Management Area" near "Pillar Point." The map also includes depth markings, geographical features, and place names, providing a detailed view of the region's natural and protected areas.

It included the following runtime statistics:

Prompt: 1051 tokens, 111.985 tokens-per-sec
Generation: 760 tokens, 17.328 tokens-per-sec
Peak memory: 21.110 GB

# 24th March 2025, 10:43 pm / vision-llms, llm-release, generative-ai, ai, qwen, llms, uv, mlx, prince-canuma, local-llms

deepseek-ai/DeepSeek-V3-0324. Chinese AI lab DeepSeek just released the latest version of their enormous DeepSeek v3 model, baking the release date into the name DeepSeek-V3-0324.

The license is MIT (that's new - previous DeepSeek v3 had a custom license), the README is empty and the release adds up a to a total of 641 GB of files, mostly of the form model-00035-of-000163.safetensors.

The model only came out a few hours ago and MLX developer Awni Hannun already has it running at >20 tokens/second on a 512GB M3 Ultra Mac Studio ($9,499 of ostensibly consumer-grade hardware) via mlx-lm and this mlx-community/DeepSeek-V3-0324-4bit 4bit quantization, which reduces the on-disk size to 352 GB.

I think that means if you have that machine you can run it with my llm-mlx plugin like this, but I've not tried myself!

llm mlx download-model mlx-community/DeepSeek-V3-0324-4bit
llm chat -m mlx-community/DeepSeek-V3-0324-4bit

The new model is also listed on OpenRouter. You can try a chat at openrouter.ai/chat?models=deepseek/deepseek-chat-v3-0324:free.

Here's what the chat interface gave me for "Generate an SVG of a pelican riding a bicycle":

I have two API keys with OpenRouter - one of them worked with the model, the other gave me a No endpoints found matching your data policy error - I think because I had a setting on that key disallowing models from training on my activity. The key that worked was a free key with no attached billing credentials.

For my working API key the llm-openrouter plugin let me run a prompt like this:

llm install llm-openrouter
llm keys set openrouter
# Paste key here
llm -m openrouter/deepseek/deepseek-chat-v3-0324:free "best fact about a pelican"

Here's that "best fact" - the terminal output included Markdown and an emoji combo, here that's rendered.

One of the most fascinating facts about pelicans is their unique throat pouch, called a gular sac, which can hold up to 3 gallons (11 liters) of water—three times more than their stomach!

Here’s why it’s amazing:
- Fishing Tool: They use it like a net to scoop up fish, then drain the water before swallowing.
- Cooling Mechanism: On hot days, pelicans flutter the pouch to stay cool by evaporating water.
- Built-in "Shopping Cart": Some species even use it to carry food back to their chicks.

Bonus fact: Pelicans often fish cooperatively, herding fish into shallow water for an easy catch.

Would you like more cool pelican facts? 🐦🌊

In putting this post together I got Claude to build me this new tool for finding the total on-disk size of a Hugging Face repository, which is available in their API but not currently displayed on their website.

Update: Here's a notable independent benchmark from Paul Gauthier:

DeepSeek's new V3 scored 55% on aider's polyglot benchmark, significantly improving over the prior version. It's the #2 non-thinking/reasoning model, behind only Sonnet 3.7. V3 is competitive with thinking models like R1 & o3-mini.

# 24th March 2025, 3:04 pm / llm-release, hugging-face, generative-ai, deepseek, ai, llms, mlx, llm, ai-assisted-programming, tools, pelican-riding-a-bicycle, openrouter, local-llms

simonw/ollama-models-atom-feed. I setup a GitHub Actions + GitHub Pages Atom feed of scraped recent models data from the Ollama latest models page - Ollama remains one of the easiest ways to run models on a laptop so a new model release from them is worth hearing about.

I built the scraper by pasting example HTML into Claude and asking for a Python script to convert it to Atom - here's the script we wrote together.

Update 25th March 2025: The first version of this included all 160+ models in a single feed. I've upgraded the script to output two feeds - the original atom.xml one and a new atom-recent-20.xml feed containing just the most recent 20 items.

I modified the script using Google's new Gemini 2.5 Pro model, like this:

cat to_atom.py | llm -m gemini-2.5-pro-exp-03-25 \
  -s 'rewrite this script so that instead of outputting Atom to stdout it saves two files, one called atom.xml with everything and another called atom-recent-20.xml with just the most recent 20 items - remove the output option entirely'

Here's the full transcript.

# 22nd March 2025, 10:04 pm / github-actions, git-scraping, ai, ollama, llms, ai-assisted-programming, generative-ai, projects, github, claude, atom, gemini, local-llms

Mistral Small 3.1. Mistral Small 3 came out in January and was a notable, genuinely excellent local model that used an Apache 2.0 license.

Mistral Small 3.1 offers a significant improvement: it's multi-modal (images) and has an increased 128,000 token context length, while still "fitting within a single RTX 4090 or a 32GB RAM MacBook once quantized" (according to their model card). Mistral's own benchmarks show it outperforming Gemma 3 and GPT-4o Mini, but I haven't seen confirmation from external benchmarks.

Despite their mention of a 32GB MacBook I haven't actually seen any quantized GGUF or MLX releases yet, which is a little surprising since they partnered with Ollama on launch day for their previous Mistral Small 3. I expect we'll see various quantized models released by the community shortly.

Update 20th March 2025: I've now run the text version on my laptop using mlx-community/Mistral-Small-3.1-Text-24B-Instruct-2503-8bit and llm-mlx:

llm mlx download-model mlx-community/Mistral-Small-3.1-Text-24B-Instruct-2503-8bit -a mistral-small-3.1
llm chat -m mistral-small-3.1

The model can be accessed via Mistral's La Plateforme API, which means you can use it via my llm-mistral plugin.

Here's the model describing my photo of two pelicans in flight:

llm install llm-mistral
# Run this if you have previously installed the plugin:
llm mistral refresh
llm -m mistral/mistral-small-2503 'describe' \
  -a https://static.simonwillison.net/static/2025/two-pelicans.jpg

The image depicts two brown pelicans in flight against a clear blue sky. Pelicans are large water birds known for their long bills and large throat pouches, which they use for catching fish. The birds in the image have long, pointed wings and are soaring gracefully. Their bodies are streamlined, and their heads and necks are elongated. The pelicans appear to be in mid-flight, possibly gliding or searching for food. The clear blue sky in the background provides a stark contrast, highlighting the birds' silhouettes and making them stand out prominently.

I added Mistral's API prices to my tools.simonwillison.net/llm-prices pricing calculator by pasting screenshots of Mistral's pricing tables into Claude.

# 17th March 2025, 6:45 pm / vision-llms, mistral, llm, generative-ai, ai, llms, ai-assisted-programming, llm-release, local-llms

mlx-community/OLMo-2-0325-32B-Instruct-4bit (via) OLMo 2 32B claims to be "the first fully-open model (all data, code, weights, and details are freely available) to outperform GPT3.5-Turbo and GPT-4o mini". Thanks to the MLX project here's a recipe that worked for me to run it on my Mac, via my llm-mlx plugin.

To install the model:

llm install llm-mlx
llm mlx download-model mlx-community/OLMo-2-0325-32B-Instruct-4bit

That downloads 17GB to ~/.cache/huggingface/hub/models--mlx-community--OLMo-2-0325-32B-Instruct-4bit.

To start an interactive chat with OLMo 2:

llm chat -m mlx-community/OLMo-2-0325-32B-Instruct-4bit

Or to run a prompt:

llm -m mlx-community/OLMo-2-0325-32B-Instruct-4bit 'Generate an SVG of a pelican riding a bicycle' -o unlimited 1

The -o unlimited 1 removes the cap on the number of output tokens - the default for llm-mlx is 1024 which isn't enough to attempt to draw a pelican.

The pelican it drew is refreshingly abstract:

# 16th March 2025, 3:30 am / llm, generative-ai, mlx, ai2, ai, llms, pelican-riding-a-bicycle, local-llms

QwQ-32B: Embracing the Power of Reinforcement Learning (via) New Apache 2 licensed reasoning model from Qwen:

We are excited to introduce QwQ-32B, a model with 32 billion parameters that achieves performance comparable to DeepSeek-R1, which boasts 671 billion parameters (with 37 billion activated). This remarkable outcome underscores the effectiveness of RL when applied to robust foundation models pretrained on extensive world knowledge.

I had a lot of fun trying out their previous QwQ reasoning model last November. I demonstrated this new QwQ in my talk at NICAR about recent LLM developments. Here's the example I ran.

LM Studio just released GGUFs ranging in size from 17.2 to 34.8 GB. MLX have compatible weights published in 3bit, 4bit, 6bit and 8bit. Ollama has the new qwq too - it looks like they've renamed the previous November release qwq:32b-preview.

# 5th March 2025, 9:10 pm / generative-ai, inference-scaling, ai, qwen, llms, open-source, mlx, ollama, llm-release, local-llms

llm-ollama 0.9.0. This release of the llm-ollama plugin adds support for schemas, thanks to a PR by Adam Compton.

Ollama provides very robust support for this pattern thanks to their structured outputs feature, which works across all of the models that they support by intercepting the logic that outputs the next token and restricting it to only tokens that would be valid in the context of the provided schema.

With Ollama and llm-ollama installed you can run even run structured schemas against vision prompts for local models. Here's one against Ollama's llama3.2-vision:

llm -m llama3.2-vision:latest \
  'describe images' \
  --schema 'species,description,count int' \
  -a https://static.simonwillison.net/static/2025/two-pelicans.jpg

I got back this:

{
    "species": "Pelicans",
    "description": "The image features a striking brown pelican with its distinctive orange beak, characterized by its large size and impressive wingspan.",
    "count": 1
}

(Actually a bit disappointing, as there are two pelicans and their beaks are brown.)

# 4th March 2025, 7:17 am / llm, ollama, plugins, generative-ai, ai, llms, llama, vision-llms, local-llms

llm-mistral 0.11. I added schema support to this plugin which adds support for the Mistral API to LLM. Release notes:

• Support for LLM schemas. #19
• -o prefix '{' option for forcing a response prefix. #18

Schemas now work with OpenAI, Anthropic, Gemini and Mistral hosted models, plus self-hosted models via Ollama and llm-ollama.

# 4th March 2025, 7:05 am / projects, mistral, llm, plugins, llms, ai, generative-ai, local-llms

Mistral Small 3 (via) First model release of 2025 for French AI lab Mistral, who describe Mistral Small 3 as "a latency-optimized 24B-parameter model released under the Apache 2.0 license."

More notably, they claim the following:

Mistral Small 3 is competitive with larger models such as Llama 3.3 70B or Qwen 32B, and is an excellent open replacement for opaque proprietary models like GPT4o-mini. Mistral Small 3 is on par with Llama 3.3 70B instruct, while being more than 3x faster on the same hardware.

Llama 3.3 70B and Qwen 32B are two of my favourite models to run on my laptop - that ~20GB size turns out to be a great trade-off between memory usage and model utility. It's exciting to see a new entrant into that weight class.

The license is important: previous Mistral Small models used their Mistral Research License, which prohibited commercial deployments unless you negotiate a commercial license with them. They appear to be moving away from that, at least for their core models:

We’re renewing our commitment to using Apache 2.0 license for our general purpose models, as we progressively move away from MRL-licensed models. As with Mistral Small 3, model weights will be available to download and deploy locally, and free to modify and use in any capacity. […] Enterprises and developers that need specialized capabilities (increased speed and context, domain specific knowledge, task-specific models like code completion) can count on additional commercial models complementing what we contribute to the community.

Despite being called Mistral Small 3, this appears to be the fourth release of a model under that label. The Mistral API calls this one mistral-small-2501 - previous model IDs were mistral-small-2312, mistral-small-2402 and mistral-small-2409.

I've updated the llm-mistral plugin for talking directly to Mistral's La Plateforme API:

llm install -U llm-mistral
llm keys set mistral
# Paste key here
llm -m mistral/mistral-small-latest "tell me a joke about a badger and a puffin"

Sure, here's a light-hearted joke for you:

Why did the badger bring a puffin to the party?

Because he heard puffins make great party 'Puffins'!

(That's a play on the word "puffins" and the phrase "party people.")

API pricing is $0.10/million tokens of input, $0.30/million tokens of output - half the price of the previous Mistral Small API model ($0.20/$0.60). for comparison, GPT-4o mini is $0.15/$0.60.

Mistral also ensured that the new model was available on Ollama in time for their release announcement.

You can pull the model like this (fetching 14GB):

ollama run mistral-small:24b

The llm-ollama plugin will then let you prompt it like so:

llm install llm-ollama
llm -m mistral-small:24b "say hi"

# 30th January 2025, 3:36 pm / open-source, mistral, llm, ollama, generative-ai, ai, llms, llm-pricing, llm-release, local-llms

Qwen2.5 VL! Qwen2.5 VL! Qwen2.5 VL! Hot on the heels of yesterday's Qwen2.5-1M, here's Qwen2.5 VL (with an excitable announcement title) - the latest in Qwen's series of vision LLMs.

They're releasing multiple versions: base models and instruction tuned models at 3B, 7B and 72B. There's a lot of additional information in their README.

The 72B model can be selected on Qwen's Qwen Chat interface. I gave it this image of our dog Cleo joy rolling on the beach:

And prompted:

Describe this image in detail, be flowery

(Since the Qwen team tends to use flowery language in their announcements.)

Here's what I got back:

In this enchanting tableau, a canine companion finds solace in the embrace of nature's softest bed. The sandy expanse stretches out like an endless canvas, its surface etched with the delicate imprints of countless wanderers who have come and gone, leaving behind a tapestry of footprints that whisper tales of joyous romps and serene strolls.

The dog, a vision of contentment, lies sprawled upon the sand, its dark fur gleaming under the gentle caress of the sun. Its body is relaxed, limbs splayed in abandon, as if it has surrendered to the soothing rhythm of the beach. A vibrant red collar adorns its neck, a splash of color against the muted tones of the surroundings, hinting at the care and love bestowed upon this cherished pet.

The sand itself is a work of art, its grains shimmering with a silvery sheen that catches the light. Here and there, small tufts of seaweed peek through, remnants of the ocean's bounty, adding a touch of wild beauty to the scene. The shadows cast by unseen objects dance across the sand, creating a play of light and dark that lends an air of mystery to the tranquil setting.

This moment, frozen in time, speaks of peace and harmony, where man's best friend finds respite in the simple pleasures of life. It is a scene that invites one to pause, breathe deeply, and revel in the serenity of nature's embrace.

I'm looking forward to trying out their smaller models - the 3B model in particular should be small enough to run comfortably even on an iPhone, so hopefully someone will wire up an example of that soon (maybe using MLX).

VB points out that the vision benchmarks for Qwen 2.5 VL 7B show it out-performing GPT-4o mini!

Qwen2.5 VL cookbooks

Qwen also just published a set of cookbook recipes:

• universal_recognition.ipynb demonstrates basic visual Q&A, including prompts like Who are these in this picture? Please give their names in Chinese and English against photos of celebrities, an ability other models have deliberately suppressed.
• spatial_understanding.ipynb demonstrates bounding box support, with prompts like Locate the top right brown cake, output its bbox coordinates using JSON format.
• video_understanding.ipynb breaks a video into individual frames and asks questions like Could you go into detail about the content of this long video?
• ocr.ipynb shows Qwen2.5-VL-7B-Instruct performing OCR in multiple different languages.
• document_parsing.ipynb uses Qwen to convert images of documents to HTML and other formats, and notes that "we introduce a unique Qwenvl HTML format that includes positional information for each component, enabling precise document reconstruction and manipulation."
• mobile_agent.ipynb runs Qwen with tool use against tools for controlling a mobile phone, similar to ChatGPT Operator or Claude Computer Use.
• computer_use.ipynb showcases "GUI grounding" - feeding in screenshots of a user's desktop and running tools for things like left clicking on a specific coordinate.

Running it with mlx-vlm

Update 30th January 2025: I got it working on my Mac using uv and mlx-vlm, with some hints from this issue. Here's the recipe that worked (downloading a 9GB model from mlx-community/Qwen2.5-VL-7B-Instruct-8bit):

uv run --with 'numpy<2' --with 'git+https://github.com/huggingface/transformers' \
  --with mlx-vlm \
  python -m mlx_vlm.generate \
    --model mlx-community/Qwen2.5-VL-7B-Instruct-8bit \
    --max-tokens 100 \
    --temp 0.0 \
    --prompt "Describe this image." \
    --image path-to-image.png

I ran that against this image:

And got back this result:

The image appears to illustrate a flowchart or diagram related to a cybersecurity scenario. Here's a breakdown of the elements:

1. User: Represented by a simple icon of a person.
2. AI Agent: Represented by a blue diamond shape.
3. Attacker: Represented by a red icon of a person.
4. Cloud and Email Icons: Represented by a cloud and an envelope, indicating data or information being transferred.
5. Text: The text

# 27th January 2025, 8:05 pm / vision-llms, generative-ai, ai, qwen, llms, prompt-engineering, ocr, uv, mlx, local-llms

Qwen2.5-1M: Deploy Your Own Qwen with Context Length up to 1M Tokens (via) Very significant new release from Alibaba's Qwen team. Their openly licensed (sometimes Apache 2, sometimes Qwen license, I've had trouble keeping up) Qwen 2.5 LLM previously had an input token limit of 128,000 tokens. This new model increases that to 1 million, using a new technique called Dual Chunk Attention, first described in this paper from February 2024.

They've released two models on Hugging Face: Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M, both requiring CUDA and both under an Apache 2.0 license.

You'll need a lot of VRAM to run them at their full capacity:

VRAM Requirement for processing 1 million-token sequences:

• Qwen2.5-7B-Instruct-1M: At least 120GB VRAM (total across GPUs).
• Qwen2.5-14B-Instruct-1M: At least 320GB VRAM (total across GPUs).

If your GPUs do not have sufficient VRAM, you can still use Qwen2.5-1M models for shorter tasks.

Qwen recommend using their custom fork of vLLM to serve the models:

You can also use the previous framework that supports Qwen2.5 for inference, but accuracy degradation may occur for sequences exceeding 262,144 tokens.

GGUF quantized versions of the models are already starting to show up. LM Studio's "official model curator" Bartowski published lmstudio-community/Qwen2.5-7B-Instruct-1M-GGUF and lmstudio-community/Qwen2.5-14B-Instruct-1M-GGUF - sizes range from 4.09GB to 8.1GB for the 7B model and 7.92GB to 15.7GB for the 14B.

These might not work well yet with the full context lengths as the underlying llama.cpp library may need some changes.

I tried running the 8.1GB 7B model using Ollama on my Mac like this:

ollama run hf.co/lmstudio-community/Qwen2.5-7B-Instruct-1M-GGUF:Q8_0

Then with LLM:

llm install llm-ollama
llm models -q qwen # To search for the model ID
# I set a shorter q1m alias:
llm aliases set q1m hf.co/lmstudio-community/Qwen2.5-7B-Instruct-1M-GGUF:Q8_0

I tried piping a large prompt in using files-to-prompt like this:

files-to-prompt ~/Dropbox/Development/llm -e py -c | llm -m q1m 'describe this codebase in detail'

That should give me every Python file in my llm project. Piping that through ttok first told me this was 63,014 OpenAI tokens, I expect that count is similar for Qwen.

The result was disappointing: it appeared to describe just the last Python file that stream. Then I noticed the token usage report:

2,048 input, 999 output

This suggests to me that something's not working right here - maybe the Ollama hosting framework is truncating the input, or maybe there's a problem with the GGUF I'm using?

I'll update this post when I figure out how to run longer prompts through the new Qwen model using GGUF weights on a Mac.

Update: It turns out Ollama has a num_ctx option which defaults to 2048, affecting the input context length. I tried this:

files-to-prompt \
  ~/Dropbox/Development/llm \
  -e py -c | \
llm -m q1m 'describe this codebase in detail' \
 -o num_ctx 80000

But I quickly ran out of RAM (I have 64GB but a lot of that was in use already) and hit Ctrl+C to avoid crashing my computer. I need to experiment a bit to figure out how much RAM is used for what context size.

Awni Hannun shared tips for running mlx-community/Qwen2.5-7B-Instruct-1M-4bit using MLX, which should work for up to 250,000 tokens. They ran 120,000 tokens and reported:

• Peak RAM for prompt filling was 22GB
• Peak RAM for generation 12GB
• Prompt filling took 350 seconds on an M2 Ultra
• Generation ran at 31 tokens-per-second on M2 Ultra

# 26th January 2025, 6:54 pm / llms, ai, qwen, generative-ai, llm, ollama, long-context, llama-cpp, llm-release, files-to-prompt, local-llms

Run DeepSeek R1 or V3 with MLX Distributed (via) Handy detailed instructions from Awni Hannun on running the enormous DeepSeek R1 or v3 models on a cluster of Macs using the distributed communication feature of Apple's MLX library.

DeepSeek R1 quantized to 4-bit requires 450GB in aggregate RAM, which can be achieved by a cluster of three 192 GB M2 Ultras ($16,797 will buy you three 192GB Apple M2 Ultra Mac Studios at $5,599 each).

# 22nd January 2025, 4:15 am / apple, generative-ai, mlx, deepseek, ai, llms, local-llms

microsoft/phi-4. Here's the official release of Microsoft's Phi-4 LLM, now officially under an MIT license.

A few weeks ago I covered the earlier unofficial versions, where I talked about how the model used synthetic training data in some really interesting ways.

It benchmarks favorably compared to GPT-4o, suggesting this is yet another example of a GPT-4 class model that can run on a good laptop.

The model already has several available community quantizations. I ran the mlx-community/phi-4-4bit one (a 7.7GB download) using mlx-llm like this:

uv run --with 'numpy<2' --with mlx-lm python -c '
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/phi-4-4bit")

prompt = "Generate an SVG of a pelican riding a bicycle"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True, max_tokens=2048)
print(response)'

Here's what I got back.

Update: The model is now available via Ollama, so you can fetch a 9.1GB model file using ollama run phi4, after which it becomes available via the llm-ollama plugin.

# 8th January 2025, 5:57 pm / phi, generative-ai, ai, microsoft, llms, uv, pelican-riding-a-bicycle, llm, ollama, llm-release, local-llms

Open WebUI. I tried out this open source (MIT licensed, JavaScript and Python) localhost UI for accessing LLMs today for the first time. It's very nicely done.

I ran it with uvx like this:

uvx --python 3.11 open-webui serve

On first launch it installed a bunch of dependencies and then downloaded 903MB to ~/.cache/huggingface/hub/models--sentence-transformers--all-MiniLM-L6-v2 - a copy of the all-MiniLM-L6-v2 embedding model, presumably for its RAG feature.

It then presented me with a working Llama 3.2:3b chat interface, which surprised me because I hadn't spotted it downloading that model. It turns out that was because I have Ollama running on my laptop already (with several models, including Llama 3.2:3b, already installed) - and Open WebUI automatically detected Ollama and gave me access to a list of available models.

I found a "knowledge" section and added all of the Datasette documentation (by dropping in the .rst files from the docs) - and now I can type # in chat to search for a file, add that to the context and then ask questions about it directly.

I selected the spatialite.rst.txt file, prompted it with "How do I use SpatiaLite with Datasette" and got back this:

That's honestly a very solid answer, especially considering the Llama 3.2 3B model from Ollama is just a 1.9GB file! It's impressive how well that model can handle basic Q&A and summarization against text provided to it - it somehow has a 128,000 token context size.

Open WebUI has a lot of other tricks up its sleeve: it can talk to API models such as OpenAI directly, has optional integrations with web search and custom tools and logs every interaction to a SQLite database. It also comes with extensive documentation.

# 27th December 2024, 1:38 am / ollama, generative-ai, llama, ai, rag, llms, uv, sqlite, python, local-llms

Meta AI release Llama 3.3. This new Llama-3.3-70B-Instruct model from Meta AI makes some bold claims:

This model delivers similar performance to Llama 3.1 405B with cost effective inference that’s feasible to run locally on common developer workstations.

I have 64GB of RAM in my M2 MacBook Pro, so I'm looking forward to trying a slightly quantized GGUF of this model to see if I can run it while still leaving some memory free for other applications.

Update: Ollama have a 43GB GGUF available now. And here's an MLX 8bit version and other MLX quantizations.

Llama 3.3 has 70B parameters, a 128,000 token context length and was trained to support English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.

The model card says that the training data was "A new mix of publicly available online data" - 15 trillion tokens with a December 2023 cut-off.

They used "39.3M GPU hours of computation on H100-80GB (TDP of 700W) type hardware" which they calculate as 11,390 tons CO2eq. I believe that's equivalent to around 20 fully loaded passenger flights from New York to London (at ~550 tons per flight).

Update 19th January 2025: On further consideration I no longer trust my estimate here: it's surprisingly hard to track down reliable numbers but I think the total CO2 used by those flights may be more in the order of 200-400 tons, so my estimate for Llama 3.3 70B should have been more in the order of between 28 and 56 flights. Don't trust those numbers either though!

# 6th December 2024, 6:30 pm / meta, generative-ai, llama, training-data, ai, local-llms, llms, ollama, llm-release

SmolVLM—small yet mighty Vision Language Model. I've been having fun playing with this new vision model from the Hugging Face team behind SmolLM. They describe it as:

[...] a 2B VLM, SOTA for its memory footprint. SmolVLM is small, fast, memory-efficient, and fully open-source. All model checkpoints, VLM datasets, training recipes and tools are released under the Apache 2.0 license.

I've tried it in a few flavours but my favourite so far is the mlx-vlm approach, via mlx-vlm author Prince Canuma. Here's the uv recipe I'm using to run it:

uv run \
  --with mlx-vlm \
  --with torch \
  python -m mlx_vlm.generate \
    --model mlx-community/SmolVLM-Instruct-bf16 \
    --max-tokens 500 \
    --temp 0.5 \
    --prompt "Describe this image in detail" \
    --image IMG_4414.JPG

If you run into an error using Python 3.13 (torch compatibility) try uv run --python 3.11 instead.

This one-liner installs the necessary dependencies, downloads the model (about 4.2GB, saved to ~/.cache/huggingface/hub/models--mlx-community--SmolVLM-Instruct-bf16) and executes the prompt and displays the result.

I ran that against this Pelican photo:

The model replied:

In the foreground of this photograph, a pelican is perched on a pile of rocks. The pelican’s wings are spread out, and its beak is open. There is a small bird standing on the rocks in front of the pelican. The bird has its head cocked to one side, and it seems to be looking at the pelican. To the left of the pelican is another bird, and behind the pelican are some other birds. The rocks in the background of the image are gray, and they are covered with a variety of textures. The rocks in the background appear to be wet from either rain or sea spray.

There are a few spatial mistakes in that description but the vibes are generally in the right direction.

On my 64GB M2 MacBook pro it read the prompt at 7.831 tokens/second and generated that response at an impressive 74.765 tokens/second.

# 28th November 2024, 8:29 pm / vision-llms, uv, mlx, ai, local-llms, llms, python, generative-ai, smollm, llm-release, prince-canuma

QwQ: Reflect Deeply on the Boundaries of the Unknown. Brand new openly licensed (Apache 2) model from Alibaba Cloud's Qwen team, this time clearly inspired by OpenAI's work on reasoning in o1.

I love the flowery language they use to introduce the new model:

Through deep exploration and countless trials, we discovered something profound: when given time to ponder, to question, and to reflect, the model’s understanding of mathematics and programming blossoms like a flower opening to the sun. Just as a student grows wiser by carefully examining their work and learning from mistakes, our model achieves deeper insight through patient, thoughtful analysis.

It's already available through Ollama as a 20GB download. I initially ran it like this:

ollama run qwq

This downloaded the model and started an interactive chat session. I tried the classic "how many rs in strawberry?" and got this lengthy but correct answer, which concluded:

Wait, but maybe I miscounted. Let's list them: 1. s 2. t 3. r 4. a 5. w 6. b 7. e 8. r 9. r 10. y Yes, definitely three "r"s. So, the word "strawberry" contains three "r"s.

Then I switched to using LLM and the llm-ollama plugin. I tried prompting it for Python that imports CSV into SQLite:

Write a Python function import_csv(conn, url, table_name) which acceopts a connection to a SQLite databse and a URL to a CSV file and the name of a table - it then creates that table with the right columns and imports the CSV data from that URL

It thought through the different steps in detail and produced some decent looking code.

Finally, I tried this:

llm -m qwq 'Generate an SVG of a pelican riding a bicycle'

For some reason it answered in Simplified Chinese. It opened with this:

生成一个SVG图像，内容是一只鹈鹕骑着一辆自行车。这听起来挺有趣的！我需要先了解一下什么是SVG，以及如何创建这样的图像。

Which translates (using Google Translate) to:

Generate an SVG image of a pelican riding a bicycle. This sounds interesting! I need to first understand what SVG is and how to create an image like this.

It then produced a lengthy essay discussing the many aspects that go into constructing a pelican on a bicycle - full transcript here. After a full 227 seconds of constant output it produced this as the final result.

I think that's pretty good!

# 27th November 2024, 11:59 pm / llm, ollama, generative-ai, ai, qwen, llms, local-llms, pelican-riding-a-bicycle, inference-scaling, llm-release

Quantization matters (via) What impact does quantization have on the performance of an LLM? been wondering about this for quite a while, now here are numbers from Paul Gauthier.

He ran differently quantized versions of Qwen 2.5 32B Instruct through his Aider code editing benchmark and saw a range of scores.

The original released weights (BF16) scored highest at 71.4%, with Ollama's qwen2.5-coder:32b-instruct-fp16 (a 66GB download) achieving the same score.

The quantized Ollama qwen2.5-coder:32b-instruct-q4_K_M (a 20GB download) saw a massive drop in quality, scoring just 53.4% on the same benchmark.

# 23rd November 2024, 6:39 pm / aider, llms, ai, generative-ai, ollama, local-llms, paul-gauthier

TextSynth Server (via) I'd missed this: Fabrice Bellard (yes, that Fabrice Bellard) has a project called TextSynth Server which he describes like this:

ts_server is a web server proposing a REST API to large language models. They can be used for example for text completion, question answering, classification, chat, translation, image generation, ...

It has the following characteristics:

• All is included in a single binary. Very few external dependencies (Python is not needed) so installation is easy.
• Supports many Transformer variants (GPT-J, GPT-NeoX, GPT-Neo, OPT, Fairseq GPT, M2M100, CodeGen, GPT2, T5, RWKV, LLAMA, Falcon, MPT, Llama 3.2, Mistral, Mixtral, Qwen2, Phi3, Whisper) and Stable Diffusion.
• [...]

Unlike many of his other notable projects (such as FFmpeg, QEMU, QuickJS) this isn't open source - in fact it's not even source available, you instead can download compiled binaries for Linux or Windows that are available for non-commercial use only.

Commercial terms are available, or you can visit textsynth.com and pre-pay for API credits which can then be used with the hosted REST API there.

This is not a new project: the earliest evidence I could find of it was this July 2019 page in the Internet Archive, which said:

Text Synth is build using the GPT-2 language model released by OpenAI. [...] This implementation is original because instead of using a GPU, it runs using only 4 cores of a Xeon E5-2640 v3 CPU at 2.60GHz. With a single user, it generates 40 words per second. It is programmed in plain C using the LibNC library.

# 21st November 2024, 5:16 am / llms, ai, generative-ai, internet-archive, gpt-2, local-llms